Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dynamic financial knowledge graph construction method based on reinforcement learning and transfer learning

A knowledge graph and reinforcement learning technology, applied in finance, neural architecture, semantic tool creation, etc., can solve the problems of inconsistent information and data from multiple parties, difficult to collect dynamic data, etc., and achieve the effect of strong practical application value and good generalization.

Inactive Publication Date: 2020-04-10
PEKING UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The difficulty of dynamic knowledge graphs lies in the difficulty of collecting dynamic data, the data inconsistency of multi-party information, and how to display this information in a user-friendly manner, etc.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dynamic financial knowledge graph construction method based on reinforcement learning and transfer learning
  • Dynamic financial knowledge graph construction method based on reinforcement learning and transfer learning
  • Dynamic financial knowledge graph construction method based on reinforcement learning and transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings.

[0049] The construction process of dynamic financial knowledge graph is as follows: figure 1 shown. The map construction process can be roughly divided into two parts: one is to build a basic dynamic financial knowledge map based on semi-structured data and structured data, and the other is to extract knowledge from unstructured data under the supervision of the basic map to expand the map. The first part is mainly engineering work, involving data processing, database construction and website construction; the second part is the focus of the invention patent, focusing on algorithm and model design.

[0050] 1. Data acquisition

[0051] The dynamic financial knowledge map constructed in the present invention is based on a large amount of crawled Internet data, which includes: A-share listed companies list, basic information and brief introduction of listed companies, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a dynamic financial knowledge graph construction method based on reinforcement learning and transfer learning. The method comprises the following steps of: 1) constructing a financial knowledge graph for structured data and semi-structured data of each selected listed company, inserting the entity reference corresponding to the financial entity in the graph into a financialentity database, 2) obtaining a financial entity data set for the unstructured data related to the selected listed company, 3) training a financial entity identification model by using the financialentity data set and the standard entity identification data set, 4) generating a financial entity link data set, and training a financial entity link model by using the financial entity link data set,5) finding a financial entity corresponding to each entity reference in the unstructured data in the financial knowledge graph by using the trained financial entity link model and updating the financial knowledge graph, and 6) performing financial entity relationship extraction from the unstructured data by using a financial relationship extraction model and updating the financial knowledge graph.

Description

technical field [0001] The invention relates to a method for constructing a dynamic financial knowledge map. The specific method is to construct a basic knowledge map using relevant structured and unstructured data of A-share listed companies, and expand and integrate the map through multiple models such as reinforcement learning and transfer learning. Optimization, and finally build and display a dynamic financial knowledge map. The invention belongs to the fields of representation learning and data analysis. Background technique [0002] 1. Dynamic financial knowledge map [0003] The name "knowledge graph" originated from the knowledge base launched by Google in 2012, which is used to support the organization of data on the network from a semantic perspective, thereby providing intelligent search services. The entities and relationships stored in the knowledge base can be completely equivalent to the nodes and edges of the graph, so the knowledge graph is gradually equa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/36G06F40/295G06Q40/00G06N3/04
CPCG06F16/367G06Q40/00G06N3/044G06N3/045
Inventor 闫宏飞张霞苗睿
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com